Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges
🤖 AI Summary
This study addresses the need for autonomous perception, reasoning, and decision-making by distributed agents in dynamic, heterogeneous wireless edge computing environments.
Method: We propose an Edge General Intelligence (EGI) architecture centered on a World Model as its cognitive core. Our approach integrates embodied intelligence with foundation models to construct a hybrid framework comprising latent representation learning, dynamics modeling, imagination-based multi-step planning, and large-model collaboration—specifically optimized for edge constraints including low latency, low power consumption, and data privacy.
Contribution/Results: We formally define the EGI technical paradigm for the first time; introduce a lightweight World Model deployment mechanism supporting digital twin integration and distributed coordination; and delineate domain-specific application pathways across vehicular networks, UAV swarms, IoT systems, and network function virtualization (NFV). These contributions establish both theoretical foundations and architectural blueprints enabling edge intelligence to evolve from reactive execution toward proactive, autonomous operation.
Application Category
📝 Abstract
Edge General Intelligence (EGI) represents a transformative evolution of edge computing, where distributed agents possess the capability to perceive, reason, and act autonomously across diverse, dynamic environments. Central to this vision are world models, which act as proactive internal simulators that not only predict but also actively imagine future trajectories, reason under uncertainty, and plan multi-step actions with foresight. This proactive nature allows agents to anticipate potential outcomes and optimize decisions ahead of real-world interactions. While prior works in robotics and gaming have showcased the potential of world models, their integration into the wireless edge for EGI remains underexplored. This survey bridges this gap by offering a comprehensive analysis of how world models can empower agentic artificial intelligence (AI) systems at the edge. We first examine the architectural foundations of world models, including latent representation learning, dynamics modeling, and imagination-based planning. Building on these core capabilities, we illustrate their proactive applications across EGI scenarios such as vehicular networks, unmanned aerial vehicle (UAV) networks, the Internet of Things (IoT) systems, and network functions virtualization, thereby highlighting how they can enhance optimization under latency, energy, and privacy constraints. We then explore their synergy with foundation models and digital twins, positioning world models as the cognitive backbone of EGI. Finally, we highlight open challenges, such as safety guarantees, efficient training, and constrained deployment, and outline future research directions. This survey provides both a conceptual foundation and a practical roadmap for realizing the next generation of intelligent, autonomous edge systems.
Problem
Research questions and friction points this paper is trying to address.
Integrating world models into wireless edge for Edge General Intelligence
Enhancing optimization in EGI scenarios under latency and energy constraints
Addressing challenges like safety guarantees and efficient training in EGI
Innovation
Methods, ideas, or system contributions that make the work stand out.
World models enable proactive simulation and planning
Agentic AI integrates with edge computing for autonomy
Synergy with foundation models and digital twins
🔎 Similar Papers
No similar papers found.
